Asr Training and Adaptation

2. The method according to claim 1, wherein selecting said LM parameters comprises retrieving, based on said comparison, said LM parameters from a database storing speaker specific LM parameters for different speakers with a respective speaker identifier and domain specific LM parameters for different program domains with a respective program domain identifier.

4. The method according to claim 1, further comprising retrieving, based on said speaker identifier, said AM parameters from a database storing speaker specific AM parameters for different speakers with a respective speaker identifier.

10. The device according to claim 9, wherein the instructions executable by the at least one processor further operate to retrieve, for each audio segment of said multiple audio segments and based on said comparison, said LM parameters from a database storing speaker specific LM parameters for different speakers with a respective speaker identifier and domain specific LM parameters for different program domains with a respective program domain identifier.

12. The device according to claim 9, wherein the instructions executable by the at least one processor further operate to select, for each audio segment of said multiple audio segments, said AM parameters based on said speaker identifier.

13. The device according to claim 9, wherein the instructions executable by the at least one processor further operate to retrieve, for each audio segment of said multiple audio segments and based on said speaker identifier, said AM parameters from a database storing speaker specific AM parameters for different speakers with a respective speaker identifier.